Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4668 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1650074 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.5210. Min Act: -0.0000

Data Index: 1476546 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.4612. Min Act: -0.0000

Data Index: 1530501 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1543520 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1615564 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1497346 (Python Code)

Max Activating Token Index: 587

Text #6

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1629000 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1580775 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2235. Min Act: -0.0000

Data Index: 1621816 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1063. Min Act: -0.0000

Data Index: 207925 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1714. Min Act: -0.0000

Data Index: 743735 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1572969 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1525. Min Act: -0.0000

Data Index: 860223 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1557. Min Act: -0.0000

Data Index: 566215 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1285. Min Act: -0.0000

Data Index: 416241 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2400. Min Act: -0.0000

Data Index: 407219 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1002. Min Act: -0.0000

Data Index: 129255 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1351. Min Act: -0.0000

Data Index: 1547771 (Python Code)

Max Activating Token Index: 309

Text #18

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0924. Min Act: -0.0000

Data Index: 242010 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1574. Min Act: -0.0000

Data Index: 119180 (C4 (Web Text))

Max Activating Token Index: 727